Backend ‐ APIs

PhotoRealistic AI API README

Please note this project is still under development and the README & the code are still being updated.

This folder contains the backend code for the Photorealistic AI project. The main purpose of the backend is to provide an API endpoint (/generate_image) to generate and return images using the trained GAN model.

Overview

The generate_images_api.py script defines a Flask web application with a single API endpoint. This endpoint is responsible for generating and returning an image using the trained GAN model.

How to Use

1. Clone the repository:

   git clone https://github.com/psavarmattas/PhotorealisticAI.git

2. Navigate to the project root:

   cd ./PhotorealisticAI

3. Install the required packages:

   pip install -r requirements.txt

4. Run the Flask application:

   python backend/generate_images_api.py

5. Once the application is running, you can make a GET request to the following endpoint to generate and receive an image:

   http://127.0.0.1:5000/generate_image

   Example using cURL:

   curl http://127.0.0.1:5000/generate_image --output generated_image.png

The Flask app will be accessible at http://127.0.0.1:5000. To generate an image, make a GET request to http://127.0.0.1:5000/generate_image.

API Endpoint

• Endpoint: /generate_image
• Method: GET
• Response: Returns the generated image in base64 format.

Note

Ensure that the GAN model is trained and saved before using the API. Refer to the main README for training instructions.

For MacOS users, please check the dependencies mentioned in the main README for compatibility.

License

Please make sure you read the license before using the code.

Attribution for the dataset

The dataset is provided by title = Deep Learning Face Attributes in the Wild author = Liu, Ziwei and Luo, Ping and Wang, Xiaogang and Tang, Xiaoou, booktitle = Proceedings of International Conference on Computer Vision (ICCV), month = December, year = 2015